def main():
parser = argparse.ArgumentParser(
description="Dependency-Guided LSTM CRF implementation")
opt = parse_arguments(parser)
conf = Config(opt)
reader = Reader(conf.digit2zero)
setSeed(opt, conf.seed)
trains = reader.read_conll(conf.train_file, -1, True)
devs = reader.read_conll(conf.dev_file, conf.dev_num, False)
tests = reader.read_conll(conf.test_file, conf.test_num, False)
if conf.context_emb != ContextEmb.none:
print('Loading the {} vectors for all datasets.'.format(
conf.context_emb.name))
conf.context_emb_size = reader.load_elmo_vec(
conf.train_file.replace(".sd", "").replace(".ud", "").replace(
".sud", "").replace(".predsd", "").replace(
".predud", "").replace(".stud", "").replace(".ssd", "") +
"." + conf.context_emb.name + ".vec", trains)
reader.load_elmo_vec(
conf.dev_file.replace(".sd", "").replace(".ud", "").replace(
".sud", "").replace(".predsd", "").replace(
".predud", "").replace(".stud", "").replace(".ssd", "") +
"." + conf.context_emb.name + ".vec", devs)
reader.load_elmo_vec(
conf.test_file.replace(".sd", "").replace(".ud", "").replace(
".sud", "").replace(".predsd", "").replace(
".predud", "").replace(".stud", "").replace(".ssd", "") +
"." + conf.context_emb.name + ".vec", tests)
conf.use_iobes(trains + devs + tests)
conf.build_label_idx(trains)
conf.build_deplabel_idx(trains + devs + tests)
print("# deplabels: ", len(conf.deplabels))
print("dep label 2idx: ", conf.deplabel2idx)
conf.build_word_idx(trains, devs, tests)
conf.build_emb_table()
conf.map_insts_ids(trains + devs + tests)
print("num chars: " + str(conf.num_char))
# print(str(config.char2idx))
print("num words: " + str(len(conf.word2idx)))
# print(config.word2idx)
if opt.mode == "train":
if conf.train_num != -1:
random.shuffle(trains)
trains = trains[:conf.train_num]
learn_from_insts(conf, conf.num_epochs, trains, devs, tests)
else:
## Load the trained model.
test_model(conf, tests)
# pass
print(opt.mode)
def main():
parser = argparse.ArgumentParser(
description="Dependency-Guided LSTM CRF implementation")
opt = parse_arguments(parser)
conf = Config(opt)
reader = Reader(conf.digit2zero)
setSeed(opt, conf.seed)
trains = reader.read_conll(conf.train_file, -1, True)
devs = reader.read_conll(conf.dev_file, conf.dev_num, False)
tests = reader.read_conll(conf.test_file, conf.test_num, False)
conf.use_iobes(trains)
conf.build_label_idx(trains)
conf.build_deplabel_idx(trains + devs + tests)
print("# deplabels: ", len(conf.deplabels))
print("dep label 2idx: ", conf.deplabel2idx)
conf.build_word_idx(trains + devs + tests)
conf.build_emb_table()
conf.map_insts_ids(trains)
print("num chars: " + str(conf.num_char))
# print(str(config.char2idx))
print("num words: " + str(len(conf.word2idx)))
# print(config.word2idx)
if opt.mode == "train":
if conf.train_num != -1:
random.shuffle(trains)
trains = trains[:conf.train_num]
learn_from_insts(conf, conf.num_epochs, trains)
print(opt.mode)
